Title :
The science of making ERORS: what error tolerance implies for capacity in neural networks
Author :
Venkatesh, Santosh S.
Author_Institution :
Dept. of Electr. Eng., Pennsylvania Univ., Philadelphia, PA, USA
fDate :
4/1/1992 12:00:00 AM
Abstract :
Discusses the development of formal protocols for handling error tolerance which allow a precise determination of the computational gains that may be expected. The error protocols are illustrated in the framework of a densely interconnected neural network architecture (with associative memory the putative application), and rigorous calculations of capacity ar shown. Explicit capacities are also derived for the case of feedforward neural network configurations
Keywords :
content-addressable storage; fault tolerant computing; neural nets; protocols; associative memory; densely interconnected neural network architecture; error protocols; error tolerance; feedforward neural network configurations; formal protocols; neural networks; Associative memory; Computer architecture; Computer networks; Intelligent networks; Memory architecture; Military computing; Neural networks; Neurons; Protocols; Recurrent neural networks;
Journal_Title :
Knowledge and Data Engineering, IEEE Transactions on
